.

requirements.txt

@@ -8,6 +8,7 @@ pydantic-settings>=2.10.1
 
 spaces
 accelerate
+autoawq
 
 vllm>=0.10.0
 torch>=2.7.1

transformers_backend.py

@@ -34,7 +34,7 @@ class TransformersChatBackend(ChatBackend):
 
         # Run inside ZeroGPU lease
         if spaces:
-            @spaces.GPU(duration=60)
+            @spaces.GPU(duration=300)
             def run_once(prompt: str) -> str:
                 tokenizer = AutoTokenizer.from_pretrained(model_id)
                 model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")